Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3044 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.2444. Min Act: -0.0000

Data Index: 1177644 (C4 (Web Text))

Max Activating Token Index: 953

Text #1

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.2528. Min Act: -0.0000

Data Index: 783186 (C4 (Web Text))

Max Activating Token Index: 465

Text #2

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.2601. Min Act: -0.0000

Data Index: 938198 (C4 (Web Text))

Max Activating Token Index: 355

Text #3

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.2521. Min Act: -0.0001

Data Index: 411260 (C4 (Web Text))

Max Activating Token Index: 614

Text #4

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.2326. Min Act: -0.0000

Data Index: 42618 (C4 (Web Text))

Max Activating Token Index: 414

Text #5

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.2364. Min Act: -0.0000

Data Index: 178500 (C4 (Web Text))

Max Activating Token Index: 449

Text #6

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.2634. Min Act: -0.0000

Data Index: 293196 (C4 (Web Text))

Max Activating Token Index: 765

Text #7

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.2481. Min Act: -0.0000

Data Index: 1135896 (C4 (Web Text))

Max Activating Token Index: 326

Text #8

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.2107. Min Act: -0.0000

Data Index: 878096 (C4 (Web Text))

Max Activating Token Index: 696

Text #9

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.2261. Min Act: -0.0000

Data Index: 1190028 (C4 (Web Text))

Max Activating Token Index: 678

Text #10

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.2239. Min Act: -0.0000

Data Index: 780622 (C4 (Web Text))

Max Activating Token Index: 489

Text #11

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.1924. Min Act: -0.0000

Data Index: 414453 (C4 (Web Text))

Max Activating Token Index: 845

Text #12

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.2227. Min Act: -0.0000

Data Index: 1290116 (C4 (Web Text))

Max Activating Token Index: 134

Text #13

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.1945. Min Act: -0.0000

Data Index: 1354944 (C4 (Web Text))

Max Activating Token Index: 851

Text #14

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.2286. Min Act: -0.0000

Data Index: 1236668 (C4 (Web Text))

Max Activating Token Index: 935

Text #15

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.2066. Min Act: -0.0000

Data Index: 392213 (C4 (Web Text))

Max Activating Token Index: 800

Text #16

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.1863. Min Act: -0.0000

Data Index: 462529 (C4 (Web Text))

Max Activating Token Index: 262

Text #17

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.1994. Min Act: -0.0000

Data Index: 1100826 (C4 (Web Text))

Max Activating Token Index: 44

Text #18

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.1942. Min Act: -0.0000

Data Index: 1078888 (C4 (Web Text))

Max Activating Token Index: 171

Text #19

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.1788. Min Act: -0.0000

Data Index: 1173511 (C4 (Web Text))

Max Activating Token Index: 798